# Omni Demand Understanding: A Benchmark for Contextual User-Intent Inference in Multimodal Interaction

arXiv: https://arxiv.org/abs/2609.21392 · HTML: https://mlsanity.com/paper/2609.21392/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 28 references that are in the map.
- First posted on arXiv 18 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Qwen2.5-Omni Technical Report](https://mlsanity.com/paper/2503.20215/) (2025)
- [Qwen3-Omni Technical Report](https://mlsanity.com/paper/2509.17765/) (2025)
- [Qwen3.5-Omni Technical Report](https://mlsanity.com/paper/2604.15804/) (2026)
- [Full-Duplex-Bench: A Benchmark to Evaluate Full-duplex Spoken Dialogue Models on Turn-taking Capabilities](https://mlsanity.com/paper/2503.04721/) (2025)
- [Seed2.0 Model Card: Towards Intelligence Frontier for Real-World Complexity](https://mlsanity.com/paper/2607.00248/) (2026)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [video-SALMONN 2: Caption-Enhanced Audio-Visual Large Language Models](https://mlsanity.com/paper/2506.15220/) (2025)
- [Full-Duplex-Bench-v2: A Multi-Turn Evaluation Framework for Duplex Dialogue Systems with an Automated Examiner](https://mlsanity.com/paper/2510.07838/) (2025)
- [Nemotron 3 Nano Omni: Efficient and Open Multimodal Intelligence](https://mlsanity.com/paper/2604.24954/) (2026)
- [MIntRec2.0: A Large-scale Benchmark Dataset for Multimodal Intent Recognition and Out-of-scope Detection in Conversations](https://mlsanity.com/paper/2403.10943/) (2024)
- [Ming-Flash-Omni: A Sparse, Unified Architecture for Multimodal Perception and Generation](https://mlsanity.com/paper/2510.24821/) (2025)
- [MTR-DuplexBench: Towards a Comprehensive Evaluation of Multi-Round Conversations for Full-Duplex Speech Language Models](https://mlsanity.com/paper/2511.10262/) (2025)
- [OmniPro: A Comprehensive Benchmark for Omni-Proactive Streaming Video Understanding](https://mlsanity.com/paper/2605.18577/) (2026)
- [Benchmarking Egocentric Multimodal Goal Inference for Assistive Wearable Agents](https://mlsanity.com/paper/2510.22443/) (2025)
- [MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions](https://mlsanity.com/paper/2507.10859/) (2025)
- [Text Takes Over: A Study of Modality Bias in Multimodal Intent Detection](https://mlsanity.com/paper/2508.16122/) (2025)
- [GUIDE: A Benchmark for Understanding and Assisting Users in Open-Ended GUI Tasks](https://mlsanity.com/paper/2603.25864/) (2026)
- [OmniInteract: Benchmarking Real-World Streaming Interaction for Real-Time Omnimodal Assistants](https://mlsanity.com/paper/2605.26485/) (2026)
- [EgoIntrospect: An Egocentric Dataset and Benchmark for User-Centric Internal State Reasoning](https://mlsanity.com/paper/2605.17262/) (2026)
- [VideoFDB: Evaluating Full-Duplex Vision-Speech Capabilities in Conversational Agents](https://mlsanity.com/paper/2605.30256/) (2026)

## Built on by (most cited first, 1 of 1)

- [Qwen3.8-Omni: Towards Native Omni-Modal Agents](https://mlsanity.com/paper/2609.25611/) (2026)

## Abstract (arXiv)

Natural audio-visual interaction is emerging as an important interface for AI assistants, allowing users to communicate through speech and vision rather than carefully composed text prompts. However, existing benchmarks of interactive capabilities still focus primarily on response quality, leaving a more fundamental question underexplored: can a model correctly infer the user's underlying demand from complex multimodal interaction? Real-world user demands are often underspecified in speech and must be inferred from multimodal cues and dialogue history. This inference is further complicated by ambiguous or disfluent expression and noisy acoustic environments. Conversely, request-like speech may not constitute a demand to the assistant, leading to false triggers. We establish Omni Demand Understanding (ODU) as a distinct multimodal contextual inference problem: given an interaction stream, a model must detect whether a user demand is present and infer intent from multimodal and conversational context. ODU evaluates this capability along five dimensions, covering both single-turn and multi-turn interactions. We construct ODU-Bench using a challenge-driven taxonomy, taxonomy-guided agentic video generation, and human-recorded interactions, followed by media-grounded annotation and human verification. We evaluate 14 native MLLMs. Even the strongest, Gemini 3.1 Pro, recovers only 44.7% of key information that must be inferred from visual, acoustic, or conversational context. Moreover, 11 of the 14 models exhibit false-trigger rates above 50% on non-demand scenarios. These results reveal a systematic capability gap in current MLLMs' ability to infer contextual user demands. We hope ODU can establish the evaluation of a previously underexplored yet essential capability in multimodal interaction: correctly understanding user demands before generating an appropriate response.